# Active vision for dexterous grasping of novel objects

arXiv: https://arxiv.org/abs/1708.04185 · HTML: https://mlsanity.com/paper/1708.04185/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Aug 2017.

## Built on by (most cited first, 4 of 4)

- [ACTIVE-o3: Empowering MLLMs with Active Perception via Pure Reinforcement Learning](https://mlsanity.com/paper/2505.21457/) (2025)
- [An Object SLAM Framework for Association, Mapping, and High-Level Tasks](https://mlsanity.com/paper/2305.07299/) (2023)
- [BFA: Best-Feature-Aware Fusion for Multi-View Fine-grained Manipulation](https://mlsanity.com/paper/2502.11161/) (2025)
- [Learning the Next Best View for 3D Point Clouds via Topological Features](https://mlsanity.com/paper/2103.02789/) (2021)

## Abstract (arXiv)

How should a robot direct active vision so as to ensure reliable grasping? We answer this question for the case of dexterous grasping of unfamiliar objects. By dexterous grasping we simply mean grasping by any hand with more than two fingers, such that the robot has some choice about where to place each finger. Such grasps typically fail in one of two ways, either unmodeled objects in the scene cause collisions or object reconstruction is insufficient to ensure that the grasp points provide a stable force closure. These problems can be solved more easily if active sensing is guided by the anticipated actions. Our approach has three stages. First, we take a single view and generate candidate grasps from the resulting partial object reconstruction. Second, we drive the active vision approach to maximise surface reconstruction quality around the planned contact points. During this phase, the anticipated grasp is continually refined. Third, we direct gaze to improve the safety of the planned reach to grasp trajectory. We show, on a dexterous manipulator with a camera on the wrist, that our approach (80.4% success rate) outperforms a randomised algorithm (64.3% success rate).